Teaching Neural Module Networks to Do Arithmetic
On the map: LLM reasoning → Mathematical reasoning
Abstract (arXiv)
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However, NMNs only have limited reasoning abilities, and lack numerical reasoning capability. We up-grade NMNs by: (a) bridging the gap between its interpreter and the complex questions; (b) introducing addition and subtraction modules that perform numerical reasoning over numbers. On a subset of DROP, experimental results show that our proposed methods enhance NMNs' numerical reasoning skills by 17.7% improvement of F1 score and significantly outperform previous state-of-the-art models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 13 references that are in the map. First posted on arXiv 6 Oct 2022.
Builds on
11 of 13 references.
References · 11
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
- 2015Neural Module Networkscited by 375
- 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
- 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
- 2019Neural Module Networks for Reasoning over Textcited by 65
- 2019NumNet: Machine Reading Comprehension with Numerical Reasoningcited by 59
- 2020Question Directed Graph Attention Network for Numerical Reasoning over Textcited by 35
- 2021Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoningcited by 10
- 2021Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Textcited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
- 2025RM-PoT: Reformulating Mathematical Problems and Solving via Program of Thoughts
- 2022NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks
- 2022Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
- 2024Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
- 2023Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
- 2024Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models
- 2026ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning